Hacker News: ildari

New comment by ildari in "GitHub's Fake Star Economy"

ildari — Mon, 20 Apr 2026 11:34:46 +0000

Bots are killing opensource, but they pump product metrics so nobody cares. I maintain an open source repo and we've made a decision to limit all bot activity, even if it makes us less sexy in front of VCs.

We figured out a workaround to limit activity to prior contributors only, and add a CI job that pushes a coauthored commit after passing captcha on our website. It cut the AI slop by 90%. Full write-up https://archestra.ai/blog/only-responsible-ai

New comment by ildari in "Let's talk about AI slop in open source"

ildari — Fri, 17 Apr 2026 12:03:40 +0000

Yeah, this is a real issue. A few weeks ago during the LiteLLM vulnerability the attacker left hundreds of bot comments under the issue to bury the conversation: https://github.com/BerriAI/litellm/issues/24512

New comment by ildari in "Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections"

ildari — Wed, 15 Oct 2025 09:22:06 +0000

This is a topic I haven't addressed in the article. There are two answer types: "guessable" (discussed here) and unguessable (such as unique IDs, emails, etc.). For the second case, the main LLM can request a quarantined LLM to store the result at the controller level and only return a reference to this data. This data is then exposed only at the end of the AI agent's execution to prevent influencing its actions.

New comment by ildari in "Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections"

ildari — Tue, 14 Oct 2025 17:58:07 +0000

The idea is that quarantined LLM has access to untrusted data, but doesn't have access to any tools or sensitive data.

The main LLM does have access to the tools or sensitive data, but doesn't have direct access to untrusted data (quarantine LLM is restricted at the controller level to respond only with integer digits, and only to legitimate questions from the main llm)

New comment by ildari in "Show HN: Open-Source Gateway to Stop Tool-Abusing Prompt Injections"

ildari — Mon, 13 Oct 2025 15:45:02 +0000

It is quite simple to start it with n8n https://www.archestra.ai/docs/platform-n8n-example and experiment with Dual LLM protection

New comment by ildari in "Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections"

ildari — Mon, 13 Oct 2025 15:42:25 +0000

external data is unavoidable for the properly functioning agent, so we have to learn to cook it

New comment by ildari in "Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections"

ildari — Mon, 13 Oct 2025 14:28:34 +0000

Most mcp endpoints don’t run any models, the main model decides which tools the ai agent should execute, and if the agent passes results back into context, that opens the door to prompt injections.

It’s really a cat-and-mouse game, where for each new model version, new jailbreaks and injections are found

New comment by ildari in "Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections"

ildari — Mon, 13 Oct 2025 13:51:24 +0000

Hi HN, I'm Ildar from Archestra, we build an open-source LLM gateway. We've been exploring ways to protect AI agents from prompt injections during tool calls and added the approach, inspired by the game "Guess Who", where the agent can learn what it needs without ever seeing the actual result. See the details in the blog post we wrote

Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections

ildari — Mon, 13 Oct 2025 13:51:24 +0000

Article URL: https://www.archestra.ai/blog/dual-llm

Comments URL: https://news.ycombinator.com/item?id=45568339

Points: 6

# Comments: 11

New comment by ildari in "Grafana releases OnCall open source project"

ildari — Tue, 14 Jun 2022 17:22:04 +0000

Hey HN, Ildar here, one of the co-founders of Amixr and one of the software engineers behind Grafana OnCall. Finally we open-sourced the product I'm really excited about that. Please try it out and leave your feedback

Best PagerDuty Alternatives 2020

ildari — Fri, 30 Oct 2020 07:41:45 +0000

Article URL: https://statusgator.com/blog/2020/09/24/best-pager-duty-alternatives/

Comments URL: https://news.ycombinator.com/item?id=24939985

Points: 2

# Comments: 0

New comment by ildari in "Microsoft Teams outage due to expired certificate"

ildari — Mon, 03 Feb 2020 23:17:29 +0000

Hi, I'm a co-founder of Amixr and we've developed curler.amixr.io, which monitors a website and delivers email notifications for free and also has an integration with our flagship product Alert Mixer

New comment by ildari in "Invent More, Toil Less (2016) [pdf]"

ildari — Sat, 16 Mar 2019 20:04:15 +0000

Is there any tool to count toil?

Toil Budget with Amixr

ildari — Thu, 21 Feb 2019 13:39:28 +0000

Article URL: https://medium.com/@iskhakov/toil-budget-with-amixr-ad299059f61f

Comments URL: https://news.ycombinator.com/item?id=19216760

Points: 3

# Comments: 0

Show HN: Curler – Dead Simple Uptime Monitoring

ildari — Thu, 07 Feb 2019 12:38:00 +0000

Article URL: http://curler.amixr.io

Comments URL: https://news.ycombinator.com/item?id=19104819

Points: 4

# Comments: 0